Show the code
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
df = pd.read_csv('../data/historic_cleaned.csv')
#df.drop(columns=['Unnamed: 0'],inplace=True)Import Data Set
Import Data Set
Display Summary Statistics of The Dataset
Show the code
df.describe()| long | lat | year | treecanopy_percent | Ann_Herb_percent | Bare_percent | Herb_percent | Litter_percent | Shrub_percent | DrySoilDays_Summer_whole | ... | PPT_Winter | PPT_Summer | T_Winter | T_Summer | Tmax_Summer | Tmin_Winter | VWC_Winter_whole | VWC_Spring_whole | VWC_Summer_whole | VWC_Fall_whole | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | ... | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 | 4407.000000 |
| mean | -110.006345 | 37.608168 | 1999.000000 | 8.895274 | 0.223796 | 55.466142 | 9.217265 | 11.412204 | 8.895274 | 7.563876 | ... | 6.534697 | 7.477377 | -0.114912 | 22.433525 | 35.909020 | -15.539766 | 0.119381 | 0.109530 | 0.068327 | 0.093987 |
| std | 0.022618 | 0.016201 | 11.255906 | 7.836078 | 1.040234 | 19.097044 | 3.812657 | 6.042003 | 7.836078 | 20.904837 | ... | 3.446036 | 2.980412 | 1.407679 | 1.029859 | 1.335224 | 3.130615 | 0.037845 | 0.039645 | 0.018993 | 0.028630 |
| min | -110.047000 | 37.570000 | 1980.000000 | 0.000000 | 0.000000 | 9.910000 | 1.010000 | 1.053000 | 0.000000 | 0.000000 | ... | 1.830000 | 2.480000 | -3.435000 | 19.555000 | 32.150000 | -26.250000 | 0.033000 | 0.035000 | 0.030000 | 0.031000 |
| 25% | -110.027000 | 37.598000 | 1989.000000 | 0.000000 | 0.000000 | 41.964000 | 7.368000 | 7.080000 | 0.000000 | 0.000000 | ... | 3.850000 | 5.710000 | -1.218000 | 21.715000 | 34.950000 | -17.250000 | 0.091000 | 0.079000 | 0.052000 | 0.074000 |
| 50% | -110.006000 | 37.609000 | 1999.000000 | 8.108000 | 0.000000 | 54.310000 | 9.709000 | 9.677000 | 8.108000 | 0.000000 | ... | 6.150000 | 7.130000 | -0.135000 | 22.327000 | 35.950000 | -14.950000 | 0.119000 | 0.102000 | 0.067000 | 0.093000 |
| 75% | -109.991000 | 37.622000 | 2009.000000 | 15.789000 | 0.000000 | 68.421000 | 10.989000 | 15.094000 | 15.789000 | 0.000000 | ... | 7.530000 | 9.480000 | 0.969000 | 23.207000 | 37.050000 | -13.800000 | 0.144500 | 0.139000 | 0.083000 | 0.111000 |
| max | -109.966000 | 37.635000 | 2018.000000 | 26.126000 | 5.085000 | 97.895000 | 20.202000 | 28.235000 | 26.126000 | 89.000000 | ... | 17.270000 | 17.890000 | 3.393000 | 24.550000 | 38.550000 | -9.350000 | 0.233000 | 0.215000 | 0.119000 | 0.205000 |
8 rows × 24 columns
Distribution of Vegetation Types
Show the code
# This code refers to https://matplotlib.org/stable/gallery/subplots_axes_and_figures/subplots_demo.html, which talks about subplots in python.
plt.figure(figsize=(14, 7))
plt.subplot(2, 3, 1)
sns.histplot(df['treecanopy_percent'], kde=True, bins=30)
plt.title('Tree Canopy Distribution')
plt.subplot(2, 3, 2)
sns.histplot(df['Ann_Herb_percent'], kde=True, bins=30)
plt.title('Annual Herbaceous Distribution')
plt.subplot(2, 3, 3)
sns.histplot(df['Bare_percent'], kde=True, bins=30)
plt.title('Bare Ground Distribution')
plt.subplot(2, 3, 4)
sns.histplot(df['Herb_percent'], kde=True, bins=30)
plt.title('Herbaceous Distribution')
plt.subplot(2, 3, 5)
sns.histplot(df['Litter_percent'], kde=True, bins=30)
plt.title('Litter Distribution')
plt.subplot(2, 3, 6)
sns.histplot(df['Shrub_percent'], kde=True, bins=30)
plt.title('Shrub Distribution')
plt.tight_layout()
plt.show()/Users/modomodo/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
with pd.option_context('mode.use_inf_as_na', True):
/Users/modomodo/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
with pd.option_context('mode.use_inf_as_na', True):
/Users/modomodo/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
with pd.option_context('mode.use_inf_as_na', True):
/Users/modomodo/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
with pd.option_context('mode.use_inf_as_na', True):
/Users/modomodo/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
with pd.option_context('mode.use_inf_as_na', True):
/Users/modomodo/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
with pd.option_context('mode.use_inf_as_na', True):
Seasonal Climate Factors
Show the code
plt.figure(figsize=(14, 7))
plt.subplot(2, 2, 1)
sns.histplot(df['T_Winter'], kde=True, bins=30)
plt.title('Winter Temperature Distribution')
plt.subplot(2, 2, 2)
sns.histplot(df['T_Summer'], kde=True, bins=30)
plt.title('Summer Temperature Distribution')
plt.subplot(2, 2, 3)
sns.histplot(df['PPT_Winter'], kde=True, bins=30)
plt.title('Winter Precipitation Distribution')
plt.subplot(2, 2, 4)
sns.histplot(df['PPT_Summer'], kde=True, bins=30)
plt.title('Summer Precipitation Distribution')
plt.tight_layout()
plt.show()/Users/modomodo/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
with pd.option_context('mode.use_inf_as_na', True):
/Users/modomodo/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
with pd.option_context('mode.use_inf_as_na', True):
/Users/modomodo/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
with pd.option_context('mode.use_inf_as_na', True):
/Users/modomodo/anaconda3/lib/python3.11/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
with pd.option_context('mode.use_inf_as_na', True):
Heat Map
Show the code
numeric_cols =df.select_dtypes(include=[np.number])
correlation_matrix = numeric_cols.corr()
plt.figure(figsize=(16, 10))
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', linewidths=0.5)
plt.title('Correlation Matrix of Climate Factors and Vegetation Types')
plt.show()